MCP Server

The Gumlet Model Context Protocol (MCP) server enables AI-powered code editors like Cursor and Windsurf, plus general-purpose tools like Claude Desktop, to interact directly with your Gumlet API and documentation.

What is MCP?

Model Context Protocol (MCP) is an open standard that allows AI applications to securely access external data sources and tools. The Gumlet MCP server provides AI agents with:

• Direct API access to Gumlet functionality
• Documentation search capabilities
• Real-time data from your Gumlet account
• Code generation assistance for Gumlet integrations

Gumlet MCP Server Setup

Gumlet hosts a remote MCP server at https://docs.gumlet.com/mcp. Configure your AI development tools to connect to this server. If your APIs require authentication, you can pass in headers via query parameters or however headers are configured in your MCP client.

{
  "mcpServers": {
    "gumlet": {
      "url": "https://docs.gumlet.com/mcp"
    }
  }
}

Testing Your MCP Setup

Once configured, you can test your MCP server connection:

1. Open your AI editor (Cursor, Windsurf, etc.)
2. Start a new chat with the AI assistant
3. Ask about Gumlet - try questions like:
   • "How do I [common use case]?"
   • "Show me an example of [API functionality]"
   • "Create a [integration type] using Gumlet"

The AI should now have access to your Gumlet account data and documentation through the MCP server.

API Calls

If you want to execute API requests you will need to pass in an api key. You can use mcp-remote to do this. Update your mcp config to look like this.

{
    "mcpServers": {
        "gumlet": {
            "command": "npx",
            "args": [
                "mcp-remote",
                "https://docs.gumlet.com/mcp",
                "--header",
                "Authorization: Bearer ${AUTH_TOKEN}"
            ],
            "env": {
                "AUTH_TOKEN": "gumlet-0dx..."
            }
        }
    }
}